Gaga: Group Any Gaussians via 3D-aware Memory Bank

Simplify your video editing workflow with Python 📹

Code for "MatchAnything: Universal Cross-Modality Image Matching with Large-Scale Pre-Training", Arxiv 2025.

GndNet: Fast ground plane estimation and point cloud segmentation for autonomous vehicles using deep neural networks.

OpenPCDet Toolbox for LiDAR-based 3D Object Detection.

WebGL point cloud viewer for large datasets

Every authored resources 📦 (premium or open-access) to learn 3D Data Science.

Curated list of papers and resources focused on 3D Gaussian Splatting, intended to keep pace with the anticipated surge of research in the coming months.

OpenPoints: a library for easily reproducing point-based methods for point cloud understanding. The engine for [PointNeXt](https://arxiv.org/abs/2206.04670)

[CVPR2024] OneFormer3D: One Transformer for Unified Point Cloud Segmentation

Pointcept: a codebase for point cloud perception research. Latest works: PTv3 (CVPR'24 Oral), PPT (CVPR'24), OA-CNNs (CVPR'24), MSC (CVPR'23)

SADG: Segment Any Dynamic Gaussian Without Object Trackers

This is a complete package of recent deep learning methods for 3D point clouds in pytorch (with pretrained models).

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

Code for "Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds"

Cognite Reveal 3D viewer

[CVPR 2023 Highlight] Neural Kernel Surface Reconstruction

Python tools for working with KITTI data.

An extension of Open3D to address 3D Machine Learning tasks

Kernel Point Convolution implemented in PyTorch

EmbodiedSAM: Online Segment Any 3D Thing in Real Time

[ICCV'23 Workshop] SAM3D: Segment Anything in 3D Scenes

The official CLIP training codebase of Inf-CL: "Breaking the Memory Barrier: Near Infinite Batch Size Scaling for Contrastive Loss". A super memory-efficiency CLIP training scheme.

3D Reconstruction for all

Framework agnostic computer vision inference. Run 1000+ models by changing only one line of code. Supports models from transformers, timm, ultralytics, vllm, ollama and your custom model.

Straight To Shapes: Real-Time Detection of Encoded Shapes

SAM with text prompt

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…